© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118597
    Prev
    Next
    INDEX
    Explanations

    nightclub fire, cocaine, revelry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mellom
    -0.07
     Помимо
    -0.07
     päiv
    -0.06
    বার্গ
    -0.06
    之间的
    -0.06
     collectively
    -0.06
     mellan
    -0.06
     फोन
    -0.06
     জেলায়
    -0.06
     করিয়াছি
    -0.06
    POSITIVE LOGITS
     SUSY
    0.06
    ीड
    0.06
     Test
    0.05
     skór
    0.05
    difference
    0.05
    Difference
    0.05
     userRepository
    0.05
     عندهم
    0.05
     вообще
    0.05
     invo
    0.05
    Activations Density 0.037%

    No Known Activations